Edit model card

image/png

Experimental Athena v4 model. Use Alpaca format. Suitable for RP, ERP and general stuff.

I should state here that this is a HIGHLY experimental model!

Description

This repo contains fp16 files of Athena-V4.

GGUF - By TheBloke

GPTQ - By TheBloke

exl2 - by waldie

AWQ - By TheBloke

fp16 - by IkariDev+Undi95

OLD(GGUF - by IkariDev+Undi95)

Ratings:

Note: I have permission of all users to upload their ratings, i DONT screenshot random reviews without asking if i can put them here!

image/png

If you want your rating to be here, send me a message over on DC and ill put up a screenshot of it here. DC name is "ikaridev".

Models+loras used and recipe

  • Athena-v3
  • Xwin-LM/Xwin-LM-13B-V0.1
  • Undi95/PsyMedRP-v1-13B
  • cgato/Thespis-13b-v0.2
  • jondurbin/airoboros-l2-13b-3.0
Athena-v4-tmp1 = [ Athena-v3(0.85)+Xwin-LM/Xwin-LM-13B-V0.1(0.15) ]
Athena-v4-tmp2 = [ Undi95/PsyMedRP-v1-13B(0.55)+cgato/Thespis-13b-v0.2(0.45) ]

Athena-v4-tmp3 = Athena-v4-tmp1(0.55) + Athena-v4-tmp2(0.35)

Athena-v4 = Athena-v4-tmp3 + jondurbin/airoboros-l2-13b-3.0(0.1)

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Thanks to Undi95 for providing the machine for Athena v2 and Athena v3, and giving me infos about how things work. Going forward i will use a merging server provided by a friend.

Downloads last month
1,476
Safetensors
Model size
13B params
Tensor type
F32
·
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for IkariDev/Athena-v4

Merges
3 models
Quantizations
5 models